Public construction-commercial domain context schemas for @ectropy/schemas universal decision log

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

A set of efficient utilities that extend the use of JSON (streaming, estimate size, NDJSON/JSONL, etc.)

A highly efficient, isomorphic, full-featured, multilingual text search engine library, providing full-text search, fuzzy matching, phonetic scoring, document indexing and more, with micro JSON state hydration/dehydration in-browser and server-side.

Vertical-neutral agent governance contracts: registration, enrollment, capability grants, budgets, decision boundary, and identity bindings.

Agent Detection & Response — tool-agnostic detection engine that intercepts coding-agent tool calls before execution

Shared Claude Code / Codex hook wire protocol: matcher engine, stdin/exit-code/stdout codec, multi-hook merge, and hook/* session events

FAF Mk4 Scoring Kernel — WASM from faf-rust. Scores .faf (21/33) and compiles FAFb v2.

This package provides a HTTP client featuring the ability to:

Policy decision point service for producing authorisation decisions from policies and context.

CLI for Primitive's decision graph — passive decision capture, conflict gate, and team presence

Multi-agent consensus engine for the MANYA Intelligence OS — specialist routing, independent analyses, weighted confidence scoring, conflict detection, structured debate, minority opinions, consensus building, review reports, and final decision synthesis.

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

Native perf module for obsidian-tc — vector ops, BM25, sqlite-vec, V2 clustering hooks

TypeScript client for the Vaara HTTP API: accountable autonomy for every autonomous action. Conformal risk scoring, policy gating, hash-chained tamper-evident audit, named detectors.

Plannotator Pi extension - interactive plan review with annotations, annotate agent messages, and review code/PRs

ADR drift detection, content safety, and decision memory for architectural decisions

Type-level contracts for the repo's cell taxonomy, starting with the Workflow decision channel — branded Workflow<C, D, E> types plus a runtime make constructor shared across the repo's cells.

Rubric Scoring Interaction

Text analysis and assessment library in JavaScript. This library can generate interesting metrics about a text and assess these metrics to give you an assessment which can be used to improve the text.